End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: nvidia/mit-b0
 library_name: transformers
 license: other
+base_model: nvidia/mit-b0
 tags:
 - vision
 - image-segmentation
@@ -16,28 +16,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # segformer-b0-finetuned-segments-satellite-terrain
 
-This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map dataset.
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map_obstacle dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7519
-- Mean Iou: 0.1878
-- Mean Accuracy: 0.3345
-- Overall Accuracy: 0.4267
+- Loss: 0.5761
+- Mean Iou: 0.4165
+- Mean Accuracy: 0.8330
+- Overall Accuracy: 0.8330
 - Accuracy Unlabeled: nan
-- Accuracy Sand: 0.6650
-- Accuracy Cliff: 0.5425
-- Accuracy Bedrock flat: 0.6302
-- Accuracy Bedrock lowhill: 0.0260
-- Accuracy Bedrock highhill: 0.0
-- Accuracy Gravel low hill: 0.4777
-- Accuracy Gravel high hill: 0.0
-- Iou Unlabeled: nan
-- Iou Sand: 0.2677
-- Iou Cliff: 0.3318
-- Iou Bedrock flat: 0.4654
-- Iou Bedrock lowhill: 0.0233
-- Iou Bedrock highhill: 0.0
-- Iou Gravel low hill: 0.2263
-- Iou Gravel high hill: 0.0
+- Accuracy Obstacle: 0.8330
+- Iou Unlabeled: 0.0
+- Iou Obstacle: 0.8330
 
 ## Model description
 
@@ -66,12 +54,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Sand | Accuracy Cliff | Accuracy Bedrock flat | Accuracy Bedrock lowhill | Accuracy Bedrock highhill | Accuracy Gravel low hill | Accuracy Gravel high hill | Iou Unlabeled | Iou Sand | Iou Cliff | Iou Bedrock flat | Iou Bedrock lowhill | Iou Bedrock highhill | Iou Gravel low hill | Iou Gravel high hill |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:--------------:|:---------------------:|:------------------------:|:-------------------------:|:------------------------:|:-------------------------:|:-------------:|:--------:|:---------:|:----------------:|:-------------------:|:--------------------:|:-------------------:|:--------------------:|
-| 1.8578        | 2.5   | 20   | 2.0192          | 0.1541   | 0.3173        | 0.3864           | nan                | 0.5737        | 0.5136         | 0.4727                | 0.0022                   | 0.0458                    | 0.6073                   | 0.0058                    | 0.0           | 0.2967   | 0.3266    | 0.3784           | 0.0022              | 0.0151               | 0.2087              | 0.0053               |
-| 1.5269        | 5.0   | 40   | 1.8513          | 0.1835   | 0.3240        | 0.4232           | nan                | 0.5623        | 0.6031         | 0.6251                | 0.0202                   | 0.0002                    | 0.4566                   | 0.0002                    | nan           | 0.2450   | 0.3490    | 0.4532           | 0.0181              | 0.0002               | 0.2190              | 0.0002               |
-| 1.4645        | 7.5   | 60   | 1.7609          | 0.1849   | 0.3302        | 0.4221           | nan                | 0.6422        | 0.5569         | 0.6105                | 0.0228                   | 0.0                       | 0.4787                   | 0.0                       | nan           | 0.2656   | 0.3316    | 0.4573           | 0.0207              | 0.0                  | 0.2194              | 0.0                  |
-| 1.6061        | 10.0  | 80   | 1.7519          | 0.1878   | 0.3345        | 0.4267           | nan                | 0.6650        | 0.5425         | 0.6302                | 0.0260                   | 0.0                       | 0.4777                   | 0.0                       | nan           | 0.2677   | 0.3318    | 0.4654           | 0.0233              | 0.0                  | 0.2263              | 0.0                  |
+| Training Loss | Epoch  | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Obstacle | Iou Unlabeled | Iou Obstacle |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-----------------:|:-------------:|:------------:|
+| 0.6635        | 3.3333 | 20   | 0.6644          | 0.4094   | 0.8189        | 0.8189           | nan                | 0.8189            | 0.0           | 0.8189       |
+| 0.5693        | 6.6667 | 40   | 0.6445          | 0.4404   | 0.8809        | 0.8809           | nan                | 0.8809            | 0.0           | 0.8809       |
+| 0.4977        | 10.0   | 60   | 0.5761          | 0.4165   | 0.8330        | 0.8330           | nan                | 0.8330            | 0.0           | 0.8330       |
 
 
 ### Framework versions

config.json

@@ -29,24 +29,12 @@
   ],
   "id2label": {
     "0": "unlabeled",
-    "1": "sand",
-    "2": "cliff",
-    "3": "bedrock flat",
-    "4": "bedrock lowhill",
-    "5": "bedrock highhill",
-    "6": "gravel low hill",
-    "7": "gravel high hill"
+    "1": "obstacle"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "label2id": {
-    "bedrock flat": 3,
-    "bedrock highhill": 5,
-    "bedrock lowhill": 4,
-    "cliff": 2,
-    "gravel high hill": 7,
-    "gravel low hill": 6,
-    "sand": 1,
+    "obstacle": 1,
     "unlabeled": 0
   },
   "layer_norm_eps": 1e-06,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d1b6b979e4b23a8decda856b7c0f123080b8fcd5613345a50d8ecaa1275c19
-size 14890952
+oid sha256:979b39becec278cb9ec201dc6ebe61743dc40d62b641bff9111817fd9a85361b
+size 14884776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1de18b969de2fa301b83d3282d88277ad0efa9fb69a4fcd94eab99e25202b6f
+oid sha256:c382888bf4883e7c19d457ce7ba896290231ac362d82cd65d070388bec3dc87f
 size 5240